"Using agents in VSCode to reference library documentation during programming" matching MCP servers:

Enables AI agents to inspect a running VS Code webview or extension host in real time, exposing DOM, console, state-store, performance, and message-traffic data over a stdio connection. Tool activation is config-driven, so MobX, Redux, Zustand, or Apollo store tools and backend-side tools appear only when the corresponding adapters are wired up.

Exposes eight MCP tools over streamable HTTP that let clients ingest alerts, list and diagnose incidents, analyze Terraform plan risk, propose remediations, and dry-run or execute policy-validated, approval-gated changes with automatic rollback.

Data observability for AI agents. Query alerts, monitor freshness, investigate schema drift, and trace lineage across your data warehouse via 53 MCP tools.

Fetches Langfuse observability traces directly into a VS Code coding agent's context, enabling querying and viewing trace data through natural language.

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

A secure MCP proxy server with JWT authentication, SQL guardrails, rate limiting, and Kafka audit logging, enabling enterprise-grade access control for MCP clients like Cursor and Claude Desktop.

Enables agents to interact with the Logflare API by writing JavaScript functions that run in a Vercel Sandbox, using three tools: search, execute_read, and execute_write.

Enables AI agents to interact with IBM QRadar SIEM, including querying and updating offenses, running AQL searches, managing threat intelligence reference sets, and checking console connectivity.

Enables interaction with Foreman instances to manage systems through the Model Context Protocol. It provides access to Foreman resources and tools, such as security update reports, directly within AI-powered environments like VSCode and Claude Desktop.

Provides structured, tool-based access to a Honeybadger account's API, enabling users to browse projects, inspect faults and notices, work with dashboards, alarms, and check-ins, and retrieve reference documentation such as BadgerQL. Runs in read-only mode by default, with optional write and delete operations, and can connect either through the hosted OAuth endpoint or a self-hosted stdio/Docker deployment.

MCP servers for real-time development monitoring and interactive pair programming.

MCP server that drives cdb.exe/kd.exe to provide WinDbg debugging to LLM agents, enabling crash dump analysis, live process debugging, kernel debugging, and a searchable command reference.

Enables MCP clients to authenticate with Grafana via Microsoft Entra ID SSO and verify the signed-in user's email using the whoami tool.

Analyzes log files using AI-powered tools to detect errors, patterns, and anomalies through natural language queries in Cursor IDE.

An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.

Provides cryptographically signed, tamper-evident compute usage receipts via a Model Context Protocol server, exposing tools to record usage, verify receipts, list the ledger, and verify ledger integrity without requiring any account, API key, or single cloud provider.

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

Tells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits